Research on Combination Optimization of Hyperspectral Inversion Model for Soil Cr Contamination
GUO Hong-xu1, WANG Long1, YANG Kai1, WU Fan1, DENG Yi-rong2, TANG Chang-cheng1, CHEN Zhi-liang3*, XIAO Rong-bo1*
1. Guangdong University of Technology, Guangzhou 510006, China
2. Guangdong Academy of Environmental Sciences, Guangzhou 510045, China
3. South China Institute of Environmental Science, Ministry of Ecology and Environment, Guangzhou 510535, China
摘要： 土壤重金属污染高光谱反演的特征波段提取方法和反演模型的选择是影响反演精度的关键；二者如何优化组合，提高反演精度是目前亟需解决的难题。在华南典型铬(Cr)污染区，采集了92组土壤样品，使用电感耦合等离子体质谱（inductively coupled plasma mass spectrometry, ICP-MS）检测Cr含量，并使用ASD Field Spec4地物光谱仪在实验室收集其高光谱信息。光谱信息预处理采用平滑滤波（SG）+标准正态化(SNV)+二阶微分（SD）变换组合, 减弱土壤散射和噪声的影响。选择竞争性自适应重加权采样（CARS）、逐步投影算法（SPA）、无信息变量消除（UVE）、遗传算法（GA）四种算法提取特征波段。选择多元线性回归（MLR）、偏最小二乘法（PLSR）、支持向量回归（SVR）和人工神经网络（ANN）四种反演模型建立特征波段与Cr含量之间的关系。通过对比不同特征波段提取方法和反演模型组合对土壤Cr含量反演的结果发现：采用CARS和UVE特征波段提取方法可以显著提高PLSR、MLR和SVR模型的预测效果；SPA方法能够提高ANN模型的预测效果；通过SG+SNV+SD+CARS+PLSR组合方式，提取位于800～1 000、1 400～1 700以及2 100～2 450 nm之间的98个特征波段，建模后模型验证，决定系数R2为0.97，均方根误差RMSE为5.25 mg·kg-1，平均绝对误差MAE为4.35 mg·kg-1，相对分析误差RPD为3.94，表明该模型在预测土壤Cr含量具有优异的性能。以土壤Cr污染高光谱反演为例，通过比较不同特征波段提取方法与反演模型组合的反演精度，确定最优模型，为小样本土壤重金属污染反演的建模提供了思路。
关键词：高光谱；模型组合优化；特征波段选择；反演模型
Abstract：The accurate inversion of soil heavy metal pollution in hyperspectral analysis relies on carefully selecting characteristic band extraction methods and inversion models. Finding the optimal combination of these two factors to achieve the highest system inversion accuracy remains an urgent and essential problem in this field. The present study involved the collection of 92 sets of soil samples from a typical Chromium (Cr) contaminated area in South China. The Cr content was quantified using Inductively Coupled Plasma Mass Spectrometry (ICP-MS). Additionally, the ASD Field Spec4 Spectrometer was employed to gather hyperspectral information in the laboratory. The spectral information preprocessing employed the combined SG+SNV+SD method. Here, SG refers to the Savitzky-Golay smoothing filter, SNV stands for Standard Normal Variate normalization, and SD represents second-order derivative transformation. This combined methodology was employed on the unprocessed spectral data to diminish the impact of soil scattering and noise. Consequently, it enhanced both the quality of spectral data and the precision of feature analysis. Four algorithms, namely Competitive Adaptive Reweighted Sampling (CARS), Successive Projections Algorithm (SPA), Uninformative Variable Elimination (UVE), and Genetic Algorithm (GA) were employed to extract Characteristic bands. Subsequently, the relationships between the extracted Characteristic bands and Cr content were established by using four inversion models: Multivariate Linear Regression (MLR), Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), and Artificial Neural Network (ANN). A comparative analysis of various Characteristic band extraction methods and combinations of inversion models regarding their impact on the accuracy of soil Cr content inversion determined that the SG+SNV+SD preprocessing enhances the spectral data's capability to represent characteristic information. CARS and UVE Characteristic band extraction methods can significantly enhance the predictive performance of PLSR, MLR, and SVR models. In contrast, the SPA method improves the predictive effectiveness of the ANN model. Through the combination approach of SG+SNV+SD+CARS+PLSR, a total of 98 characteristic bands located within the ranges of 800～1 000, 1 400～1 700, and 2 100～2 450 nm were extracted. Model validation yielded an R2 value of 0.97, RMSE of 5.25 mg·kg-1, MAE of 4.35 mg·kg-1, and RPD of 3.94. These evaluation metrics demonstrate the exceptional predictive capability of the model for soil Chromium Cr. In this research, soil Cr pollution was selected as a case study for hyperspectral inversion. A comparative analysis of various combinations of characteristic band selections and inversion model methods identified the optimal approach for modeling the inversion of heavy metal pollution in representative soils characterized by limited sample size and high contaminant concentrations.
Key words：Hyperspectral; Model combination optimization; Feature band selection; Inversion model
郭洪旭，王 龙，杨 凯，吴 凡，邓一荣，唐长城，陈志良，肖荣波. 土壤Cr含量高光谱反演模型组合优化研究[J]. 光谱学与光谱分析, 2024, 44(11): 3273-3279.
GUO Hong-xu, WANG Long, YANG Kai, WU Fan, DENG Yi-rong, TANG Chang-cheng, CHEN Zhi-liang, XIAO Rong-bo. Research on Combination Optimization of Hyperspectral Inversion Model for Soil Cr Contamination. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(11): 3273-3279.
[1] WANG Yue, LIU Ying-xue, LI Dan-dan, et al(王 玥，刘莹雪，李丹丹, 等). Journal of Agro-Environment Science(农业环境科学学报), 2021, 40(12): 2723.
[2] Ding S, Zhang X, Sun W, et al. Journal of Soils and Sediments, 2022, 22(5): 1431.
[3] Zhang J, Wang M, Yang K, et al. International Journal of Environmental Research and Public Health, 2022, 19(13): 7755.
[4] Wu T, Yu J, Lu J, et al. Agriculture, 2020, 10(7): 292.
[5] Hou L, Li X, Li F. Journal of Environmental Quality, 2019, 48(1): 57.
[6] Trifi M, Gasmi A, Carbone C, et al. Environmental Science and Pollution Research, 2022, 29(58): 87490.
[7] Ahmad S, Pandey A C, Kumar A, et al. Applied Geomatics, 2021, 13: 361.
[8] ZHANG Xia, SUN You-xin, SHANG Kun, et al(张 霞，孙友鑫，尚 坤, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2024, 55(1): 186.
[9] TU Yu-long, ZOU Bin, JIANG Xiao-lu, et al(涂宇龙，邹 滨，姜晓璐, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2018, 38(2): 575.
[10] AN Bai-song, WANG Xue-mei, HUANG Xiao-yu, et al(安柏耸，王雪梅，黄晓宇, 等). Earth and Environment(地球与环境), 2023, 51(2): 246.
[11] Zhao L, Hu Y M, Zhou W, et al. Sustainability, 2018, 10(7): 2474.
[12] GAO Zhong-yuan, XIAO Rong-bo, WANG Peng, et al(高中原，肖荣波，王 鹏, 等). Environmental Science(环境科学), 2021, 42(1): 343.
[13] Guo H, Yang K, Wu F, et al. Sensors, 2023, 23(21): 8756.
[14] MENG Shan, LI Xin-guo, JIAO Li(孟 珊，李新国，焦 黎). Chinese Journal of Soil Science, 2023, 54(2): 286.
[15] Akbari D. IET Image Processing, 2019, 13(12): 2169.
[16] Su L, Shi W, Chen X, et al. Food Chemistry, 2021, 338: 127797.
[17] Sekulic Z, Antanasijevic D, Stevanovic S, et al. International Journal of Environmental Science and Technology, 2017, 14(7): 1383.
[18] CHEN Jun-jian, ZHANG Hui-hua, LIU Jian-ming, et al(陈俊坚，张会化，刘鉴明, 等). Ecology and Environmental Sciences(生态环境学报), 2011, 20(4): 646.
[19] CHENG Yong-sheng, ZHOU Yao(成永生，周 瑶). The Chinese Journal of Nonferrous Metals(中国有色金属学报), 2021, 31(11): 3450.
